@inproceedings{oravecz-etal-2014-hungarian,
title = "The {H}ungarian {G}igaword Corpus",
author = "Oravecz, Csaba and
V{\'a}radi, Tam{\'a}s and
Sass, B{\'a}lint",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Loftsson, Hrafn and
Maegaard, Bente and
Mariani, Joseph and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Ninth International Conference on Language Resources and Evaluation ({LREC}'14)",
month = may,
year = "2014",
address = "Reykjavik, Iceland",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2014/pdf/681_Paper.pdf",
pages = "1719--1723",
abstract = "The paper reports on the development of the Hungarian Gigaword Corpus (HGC), an extended new edition of the Hungarian National Corpus, with upgraded and redesigned linguistic annotation and an increased size of 1.5 billion tokens. Issues concerning the standard steps of corpus collection and preparation are discussed with special emphasis on linguistic analysis and annotation due to Hungarian having some challenging characteristics with respect to computational processing. As the HGC is designed to serve as a resource for a wide range of linguistic research as well as for the interested public, a number of issues had to be resolved which were raised by trying to find a balance between the above two application areas. The following main objectives have been defined for the development of the HGC, focusing on the pivotal concept of increase in: - size: extending the corpus to minimum 1 billion words, - quality: using new technology for development and analysis, - coverage and representativity: taking new samples of language use and including further variants (transcribed spoken language data and user generated content (social media) from the internet in particular).",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="oravecz-etal-2014-hungarian">
<titleInfo>
<title>The Hungarian Gigaword Corpus</title>
</titleInfo>
<name type="personal">
<namePart type="given">Csaba</namePart>
<namePart type="family">Oravecz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tamás</namePart>
<namePart type="family">Váradi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bálint</namePart>
<namePart type="family">Sass</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2014-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC’14)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hrafn</namePart>
<namePart type="family">Loftsson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asuncion</namePart>
<namePart type="family">Moreno</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Reykjavik, Iceland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The paper reports on the development of the Hungarian Gigaword Corpus (HGC), an extended new edition of the Hungarian National Corpus, with upgraded and redesigned linguistic annotation and an increased size of 1.5 billion tokens. Issues concerning the standard steps of corpus collection and preparation are discussed with special emphasis on linguistic analysis and annotation due to Hungarian having some challenging characteristics with respect to computational processing. As the HGC is designed to serve as a resource for a wide range of linguistic research as well as for the interested public, a number of issues had to be resolved which were raised by trying to find a balance between the above two application areas. The following main objectives have been defined for the development of the HGC, focusing on the pivotal concept of increase in: - size: extending the corpus to minimum 1 billion words, - quality: using new technology for development and analysis, - coverage and representativity: taking new samples of language use and including further variants (transcribed spoken language data and user generated content (social media) from the internet in particular).</abstract>
<identifier type="citekey">oravecz-etal-2014-hungarian</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2014/pdf/681_Paper.pdf</url>
</location>
<part>
<date>2014-05</date>
<extent unit="page">
<start>1719</start>
<end>1723</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The Hungarian Gigaword Corpus
%A Oravecz, Csaba
%A Váradi, Tamás
%A Sass, Bálint
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Loftsson, Hrafn
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC’14)
%D 2014
%8 May
%I European Language Resources Association (ELRA)
%C Reykjavik, Iceland
%F oravecz-etal-2014-hungarian
%X The paper reports on the development of the Hungarian Gigaword Corpus (HGC), an extended new edition of the Hungarian National Corpus, with upgraded and redesigned linguistic annotation and an increased size of 1.5 billion tokens. Issues concerning the standard steps of corpus collection and preparation are discussed with special emphasis on linguistic analysis and annotation due to Hungarian having some challenging characteristics with respect to computational processing. As the HGC is designed to serve as a resource for a wide range of linguistic research as well as for the interested public, a number of issues had to be resolved which were raised by trying to find a balance between the above two application areas. The following main objectives have been defined for the development of the HGC, focusing on the pivotal concept of increase in: - size: extending the corpus to minimum 1 billion words, - quality: using new technology for development and analysis, - coverage and representativity: taking new samples of language use and including further variants (transcribed spoken language data and user generated content (social media) from the internet in particular).
%U http://www.lrec-conf.org/proceedings/lrec2014/pdf/681_Paper.pdf
%P 1719-1723
Markdown (Informal)
[The Hungarian Gigaword Corpus](http://www.lrec-conf.org/proceedings/lrec2014/pdf/681_Paper.pdf) (Oravecz et al., LREC 2014)
ACL
- Csaba Oravecz, Tamás Váradi, and Bálint Sass. 2014. The Hungarian Gigaword Corpus. In Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC'14), pages 1719–1723, Reykjavik, Iceland. European Language Resources Association (ELRA).